Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stead
    -0.07
    (copy
    -0.07
    069
    -0.07
     البته
    -0.07
     wr
    -0.06
     siz
    -0.06
    abble
    -0.06
     nev
    -0.06
    (course
    -0.06
    ......
    -0.06
    POSITIVE LOGITS
     groupName
    0.06
    뢰
    0.06
     рассчит
    0.06
     ощущ
    0.06
     провер
    0.06
     actualizar
    0.06
     convey
    0.06
    -Nov
    0.06
    خ
    0.06
    ００
    0.06
    Act Density 0.052%

    No Known Activations